Dynamic Time Warping (DTW) is a sequence alignment algorithm that measures similarity between two temporal signals by elastically warping them along the time axis to find the optimal alignment that minimizes cumulative distance, making it robust to variations in speed, timing, and phase. In WiFi/CSI sensing research, DTW is used to compare CSI time-series patterns against reference templates for tasks such as occupancy detection and crowd counting, enabling reliable matching even when signal fluctuations caused by human presence exhibit temporal inconsistencies across measurements. A common variant employed in these contexts is constrained DTW, which limits the warping path within a defined boundary window to reduce computational cost while preserving alignment accuracy.
Source Papers
- A Survey on Green Wireless Sensing: Energy-Efficient Sensing via WiFi CSI and Lightweight Learning ↗ — A Survey on Green Wireless Sensing: Energy-Efficient Sensing
- Device-free occupancy detection and crowd counting in smart buildings with WiFi-enabled IoT ↗ — Device-free occupancy detection and crowd counting in smart
- FreeCount: Device-Free Crowd Counting with Commodity WiFi ↗ — FreeCount: Device-Free Crowd Counting with Commodity WiFi